Google unveils new AI models to boost drug discovery

USA – Google has announced a new set of artificial intelligence (AI) models designed to support drug discovery.

The tech giant shared the update at its annual event, The Check Up, showcasing its commitment to revolutionizing healthcare through AI.

The new models, known as TxGemma, are part of Google’s broader AI framework and are built on its Gemini AI platform.

A new tool for scientists

Google’s TxGemma models are trained to understand various aspects of drug development, including chemical structures, small molecules, and proteins.

According to Dr. Karen DeSalvo, Google’s Chief Health Officer, these models will help researchers predict critical properties of potential new drugs.

“This means researchers can ask TxGemma questions to help predict important properties of potential new therapies, like how safe or effective they might be,” DeSalvo said in a blog post.

The Health AI Developer Foundations program will provide the scientific community with access to TxGemma later this month. However, it is still unclear whether these models will be available for commercial use.

AI’s role in drug development

AI is already reshaping the pharmaceutical industry by analyzing large datasets, identifying patterns, and predicting outcomes.

This technology is being used to discover drug targets, design new medications, and repurpose existing drugs.

Dr. DeSalvo emphasized the importance of AI in making drug discovery more efficient. “The development of therapeutic drugs from concept to approved use is a long and expensive process, so we’re working with the wider research community to find new ways to make this development more efficient,” she said.

Regulatory bodies have also taken notice. The U.S. Food and Drug Administration (FDA) issued its first guidelines on AI use in regulatory filings earlier this year, while the European Medicines Agency (EMA) outlined its stance on AI in a reflection paper in 2024.

More AI innovations in healthcare

Alongside TxGemma, Google highlighted several other AI-driven healthcare initiatives at The Check Up event:

• Improved health search results – Enhancing the accuracy of medical information available on Google Search.
• Health connect App – A new feature to help users access and manage their medical records.
• AI ‘Co-Scientist’ – A virtual assistant designed to assist scientists in generating research hypotheses and proposals.
• Capricorn AI tool – An AI system that helps physicians find personalized treatments for childhood cancers by analyzing public medical data and de-identified patient records.

Dr. DeSalvo provided an example of how AI can accelerate research: “Let’s say researchers want to better understand the spread of a disease-causing microbe. They can specify this research goal using natural language, and the AI co-scientist will propose testable hypotheses, including a summary of relevant published literature and a possible experimental approach.”